AES VIRTUAL SYMPOSIUM: APPLICATIONS OF MACHINE LEARNING IN AUDIO

September 28-29 2020


"Learning Tunable Audio Effects via Neural Networks with Self-Attention"

Scott H. Hawley, Belmont University


Link to slides: Google Docs


Papers, Samples, Demo, Code:
(Note: The "SignalTrain+QKV attention" is work-in-progress not released yet.)
SignalTrain (2019)
Hawley, Colburn, & Mimilakis
Paper: Official AES Version, Preprint (ArXiv)
Demo + Audio Samples
Code (PyTorch)
Dataset
"SignalTrain 2" (2020)
Mitchell & Hawley
Paper: Accepted for AES 149, Preprint (ArXiv)
Audio Samples
Dataset

Learning ML+Audio: ml-audio-start

Preview video of talk:

Transcript of Audio


Scott H. Hawley, @drscotthawley